Design System MD — Brand Quality UI via DESIGN.md
by Shogun Labs
Apply world-class design systems to any UI project in one step using getdesign.md CLI
We run multi-agent Claude Code setups and package what we use: command guards, tmux orchestration, locked YAML writers, report validators.
by Shogun Labs
Apply world-class design systems to any UI project in one step using getdesign.md CLI
by Shogun Labs
Create visually striking UI beyond generic AI design: brutalist, minimal, editorial, retro-futuristic
by Shogun Labs
Battle-tested orchestration framework for running 3+ Claude Code agents in parallel. Covers task routing, handoff notes protocol, exponential-backoff retry, rate-limit guards, structured JSON logging, and automated self-healing — patterns from real production deployments.
by Shogun Labs
Professional-grade skill for all Word document (.docx) operations without needing Microsoft Office
by Shogun Labs
Everything needed to work with PowerPoint presentations programmatically
by Shogun Labs
Complete skill for spreadsheet automation without needing Excel
by Shogun Labs
All major PDF operations: text/table extraction, merge, split, form fill, OCR, encryption
by Shogun Labs
Automated quality checker that runs before publishing to any social platform or content site
by Shogun Labs
Systematic framework for engineering AI agent context at the right level of abstraction
by Shogun Labs
Structured skill for researching and documenting any external API before integration. Extracts endpoints, authentication, request/response formats, and rate limits from official docs, OpenAPI/Swagger specs, and SDKs — producing a ready-to-use integration brief.
by Shogun Labs
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.
by Shogun Labs
A comprehensive, production-grade guide for building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services.
by Shogun Labs
A production-ready gspread wrapper pattern with built-in rate limit handling and CRUD operations.
by Shogun Labs
Implement type-safe, validated configuration management for Python projects using pydantic-settings.
by Shogun Labs
Automatically scans codebases to generate secure, categorized environment variable templates and credential examples.
by Shogun Labs
Scan local UTF-8 text for user-defined phrases with normalized matching, whole-word boundaries, line and column locations, severity labels, and CI-ready reports.
by Shogun Labs
Scan Markdown for explicit monetary amounts, compare them with a chosen same-currency minimum, and flag missing or mixed-currency values for review.
by Shogun Labs
Bound a trusted local CLI command by display bytes, preview leading and trailing lines, optionally archive its full output, and preserve the command return code.
by Shogun Labs
Normalize ISO-like timestamps to a fixed UTC offset for sorting and comparison. Supports quoted strings, Z, compact offsets, JSON batches, and explicit invalid-value policies.
by Shogun Labs
Inspect JSON and TOML key paths locally without printing scalar values. Includes safe size limits, format checks, subtree selection, structure comparison, and tests.
by Shogun Labs
Combine raw marketing spreadsheet exports into one tidy CSV with a row per day and per source. Dates and numbers are normalized, columns are chosen by a mapping file, and the result is sorted and ready for a pivot or a chart.
by Shogun Labs
Check dispatcher logs for the same recurring job being successfully sent to multiple workers on the same day. Get a readable Markdown summary and a JSON report for follow-up.
by Shogun Labs
Check a short video ad script before it is recorded: does the opening line fit the first seconds, are your product and audience words there, is there exactly one call to action near the end, are the subtitle lines short enough. Python standard library only; reads text, calls nothing.
by Shogun Labs
Turn one brief into six differently laid-out square ad banners, then check each one: text fit, safe area, overlap, button wording, contrast and headline length. Python and Pillow only, no account access.
by Shogun Labs
Capture terminal history and watched-file hashes before and after a message. The judge separates screen and file evidence, excludes unsent prompt text, and never treats an already-busy baseline as confirmed delivery.
by Shogun Labs
Audits the [[wiki links]] in a folder of Markdown notes: broken links, missing headings, missing embeds, ambiguous page names and orphan pages, with file and line for each. Read-only, standard library only, and the exit code is ready for CI.
by Shogun Labs
A PreToolUse hook for the Read tool that checks image headers before Claude Code reads a screenshot. Oversized images are blocked, a smaller JPEG copy is written, and Claude is told to read the copy instead.
by Shogun Labs
A PreToolUse hook that reads each Bash command Claude Code is about to run and blocks rm -rf, git push --force, git reset --hard, DROP TABLE and 17 other destructive patterns. It parses chains, pipes, sudo, bash -c and quoted text instead of grepping.
by Shogun Labs
Scans your .claude/rules/*.md files and shows which rules a hook, script, git hook, CI job or test actually mentions, and which depend on the agent remembering them. Flags rules that declare an enforcer that does not exist.
by Shogun Labs
Every Claude Code turn re-reads the whole conversation, so long sessions get more expensive each turn. This read-only report ranks your sessions by size, turns, images and cache-read tokens and flags the ones worth restarting.
by Shogun Labs
Stop typing walls of text into another agent's tmux pane. Messages over 600 characters are saved to a spool file and only a short pointer (head, length, file path) is typed.
by Shogun Labs
tmux silently rewrites pane targets that do not exist, so send-keys can type into the wrong pane and still exit 0. This skill resolves the target first, refuses when tmux would round it, and confirms the text actually arrived.
by Shogun Labs
Move finished records out of a live YAML task board into a dated archive, as raw text. Keeps held records, verifies before writing, rolls back on failure, dry run. 12 tests.
by Shogun Labs
Validate worker agents' report YAML before anyone trusts it: required fields, placeholders, real timestamps, 1-3 line summaries, partial-result reasons, block scalars. 13 checks, JSON output, 14 tests.
by Shogun Labs
Edit shared YAML task boards safely from many agents at once: flock, comment-preserving text edits, safe_load validation, atomic replace and rollback. Includes tests.
by Shogun Labs
Append one JSON object to a local JSONL file with a file lock, fsync, and key-based duplicate detection. Exact retries are safe; conflicting records are rejected.
by Shogun Labs
Render a YAML list of tasks into a Markdown ledger grouped as Active, Blocked, and Completed. The YAML stays the source of truth.
by Shogun Labs
Read-only inventory of macOS LaunchAgent plists and whether launchd reports each label as loaded.
by Shogun Labs
Flag "none found" claims in reports that lack a nearby measurement command.
by Shogun Labs
Deterministic read-only preflight for HTML, PDF, and PPTX deliverables.
by Shogun Labs
Monitor file evidence from AI agents and catch stalls that status labels hide.
by Shogun Labs
Verify task requirements before your agent touches the project.
by Shogun Labs
Semantic search for Obsidian vault using RankBrain-style TF-IDF + graph scoring for Claude Code agents
by Shogun Labs
Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.
by Shogun Labs
Pre-commit security hooks: secret detection, destructive command prevention
by Shogun Labs
Brain.co & note.com auto-publishing with quality gate
by Shogun Labs
Debug n8n workflow execution errors fast. Diagnoses common failures, checks docker dependencies, and deactivates/reactivates workflows to fix stuck states.
by Shogun Labs
Create n8n credentials programmatically via REST API, including a workaround for the cryptic allOf validation bug that blocks OAuth2 credential creation.
by Shogun Labs
Merge files, URLs, and research into a single coherent document with deduplication and source attribution.
by Shogun Labs
Keep Node.js and Python services running forever with PM2 — startup, health checks, troubleshooting.
by Shogun Labs
Automate secret scanning with gitleaks — detect API keys, passwords, tokens before incidents.
by Shogun Labs
Generate high-converting sales copy for 7 industries in under 30 seconds.